© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8411
    Prev
    Next
    INDEX
    Explanations

    take ... out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CIM
    -0.09
     Launcher
    -0.09
    åĤ¬
    -0.08
    ä¸įæŃ¢
    -0.08
     banquet
    -0.08
    æĸ°å½¢åĬ¿
    -0.08
    交æİ¥
    -0.08
    .props
    -0.08
    urb
    -0.07
     sideline
    -0.07
    POSITIVE LOGITS
    æİīäºĨ
    0.11
    agna
    0.10
    åİ»äºĨ
    0.10
     removed
    0.10
    åIJĪçIJĨæĢ§
    0.09
     khá»ıi
    0.09
    åİļéĩį
    0.09
     Dix
    0.09
    åħīçݯ
    0.09
    åıijå¸ĥåħ¬åijĬ
    0.09
    Activations Density 0.043%

    No Known Activations